Ideogram4 Uncensored (CLIP)
DOES NOT ELIMINATE the amount of images returned censored - It does improve results when the image is not rejected. Use of other lora's needed to bypass safety.
This is the same model as my QWEN Caption GUI uses.
If using QWEN or Gemma as a prompt enhancement either model will produce far better uncensored results.
NOTE: Unless using a bypass LORA you will still get +90% rejected results with the LLM alone.
Description
FAQ
Comments (1)
You are probably using wrong WF, because I have never seen the Image blocked by safety filter in my NSFW generations with IG4. You only need to use the json format. Not manually written of course. Just use existing tools to convert plain prompt to json.
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.